Author:
Nguyen Hoan-Viet,Bae Jun-Hee,Lee Yong-Eun,Lee Han-Sung,Kwon Ki-Ryong
Abstract
Steel is one of the most basic ingredients, which plays an important role in the machinery industry. However, the steel surface defects heavily affect its quality. The demand for surface defect detectors draws much attention from researchers all over the world. However, there are still some drawbacks, e.g., the dataset is limited accessible or small-scale public, and related works focus on developing models but do not deeply take into account real-time applications. In this paper, we investigate the feasibility of applying stage-of-the-art deep learning methods based on YOLO models as real-time steel surface defect detectors. Particularly, we compare the performance of YOLOv5, YOLOX, and YOLOv7 while training them with a small-scale open-source NEU-DET dataset on GPU RTX 2080. From the experiment results, YOLOX-s achieves the best accuracy of 89.6% mAP on the NEU-DET dataset. Then, we deploy the weights of trained YOLO models on Nvidia devices to evaluate their real-time performance. Our experiments devices consist of Nvidia Jetson Nano and Jetson Xavier AGX. We also apply some real-time optimization techniques (i.e., exporting to TensorRT, lowering the precision to FP16 or INT8 and reducing the input image size to 320 × 320) to reduce detection speed (fps), thus also reducing the mAP accuracy.
Funder
Technology Development Program
Ministry of SMEs and Startups
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference27 articles.
1. A convolutional neural network-based method for workpiece surface defect detection;Xing;Measurement,2021
2. Chen, Y., Ding, Y., Zhao, F., Zhang, E., Wu, Z., and Shao, L. (2021). Surface Defect Detection Methods for Industrial Products: A Review. Appl. Sci., 11.
3. State of the Art in Defect Detection Based on Machine Vision;Ren;Int. J. of Precis. Eng. Manuf.-Green Tech.,2022
4. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks;Ren;IEEE Trans. Pattern Anal. Mach. Intell.,2017
5. Slighter Faster R-CNN for real-time detection of steel strip surface defects;Ren;2018 Chin. Autom. Congr. (CAC),2018
Cited by
8 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献